Training in progress, step 3800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e769bfc1724ed308c205a8c14b676fae0abcbd6c25becc3bfe12e722223c07cf
+oid sha256:c1d5f735fc1982152b996e49d1c5f6328da127293e51ef73bceca4e1c2b1e27f
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74753ec518e8d2666789da18f5c923b6bc477180e32f344e5a49afb25a6e0e8d
+oid sha256:2dfef2bf7d54f763d0efd5e0b9d3a27087c659b5cd7c1cfc6aa847f8c06a3018
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef6f32abae8765ac279f01b65645da0753bd6efe11cfd496c1755d230e06403
+oid sha256:bc82e060dbeb087813f8570d4ef0d683a7cb5bc0dc56d6dc00e0c84cd7b34d06
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0821ee9d28fc01fbc262ed483413dc26739baf1e14fa4d0c91c7a556f900b29
+oid sha256:20d31eebb7ed74aa29b670f4a1178907b09cdcd684c7c072daf50f49cc9dad3b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d3848ebfcaff899018cb00e793689532c0c6ee3110dd60ff1772d5938a5bbb8
+oid sha256:0fa2d9146d3c80203b405802e7f42444a6a216553aa167001257311731741b78
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e13b7d008018a901e0404dc7c5d0954ab2a8a902f5925b2a1cf755436238ef
+oid sha256:da0c66931a0baac79fda86a1d4643855609847d8b5184185ec34959c81348839
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441414a8b2ee43835af49fbc545c51f73e6eb50f2e424bb61db75a70f48a2169
+oid sha256:efaa118bc9e720a18496866cfec00973dee8a5557f3fd9597f9df5a86a299377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7916857600212097,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3700",
-  "epoch": 4.953145917001339,
+  "epoch": 5.087014725568943,
   "eval_steps": 100,
-  "global_step": 3700,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -562,6 +562,21 @@
       "eval_samples_per_second": 892.674,
       "eval_steps_per_second": 3.607,
       "step": 3700
+    },
+    {
+      "epoch": 5.087014725568943,
+      "grad_norm": 0.19471462070941925,
+      "learning_rate": 0.0004912985274431057,
+      "loss": 0.7532,
+      "step": 3800
+    },
+    {
+      "epoch": 5.087014725568943,
+      "eval_loss": 0.8013682961463928,
+      "eval_runtime": 6.4045,
+      "eval_samples_per_second": 888.745,
+      "eval_steps_per_second": 3.591,
+      "step": 3800
     }
   ],
   "logging_steps": 100,
@@ -576,7 +591,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -590,7 +605,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.34355401834496e+17,
+  "total_flos": 1.37986628911104e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null